Claude.ai and API Unavailable

(status.claude.com)

85 points | by rob 1 hour ago

29 comments

  • aliljet 49 minutes ago
    This is a tough moment. Claude is simultaneously becoming substantially more expensive, substantially less reliable (single 9 of reliability), and substantially less performant. It's really hard to justify the cost of a subscription over there right now.
    • giancarlostoro 43 minutes ago
      There was another thread where some people pointed out, Amazon will give you access to Claude with better uptime for the same price (per million tokens up / down), downside is, it does not have the native ability to browse the web, but maybe that's a hidden blessing, since it's less likely to read some random website that has prompt injection embedded into it.

      For coding its fine, I havent experimented too much with Amazon Bedrock myself, but I just might soon to check for any limitations.

      • willsmith72 15 minutes ago
        But that's just paying per use right, not with the subscription which is way better value
    • datadrivenangel 46 minutes ago
      From an economics perspective, it makes sense to make it more expensive if you're having trouble keeping up with demand for a service. It'll be tough getting used to because it was so nice and cheap
      • a_victorp 17 minutes ago
        On the other hand, it was somewhat expected that we would have a correction for the prices. Hopefully after this correction things will be more stable and we won't have to worry too much about future price increases
    • edmundsauto 35 minutes ago
      YMMV. I would still be very happy with Claude if it hard failed on 20% of tasks. You can always come back to it.

      I say this as someone working for a tech company who does not have to foot the bill (in the >$1k per month bracket)

      I also experienced and accept the 1990s levels of unreliability, which is my “internet generation”. My first access was lifting a handset and placing on a speaker/mic cradle.

      Programmers these days are fucking spoiled. If it’s $220 worth of value for $200 - I get it. But I’m getting $100k of value for $10k and so I’ll put up with some shit.

      • willsmith72 13 minutes ago
        > If it’s $220 worth of value for $200 - I get it.

        Wrong comparison. If a competitor gives you $230 of value for $200, of course you shouldn't pick the $220 one

      • bbeonx 32 minutes ago
        lol i love this post. not 100% sure i agree, but not 100% i don't. but great post, 10/10
      • wahnfrieden 31 minutes ago
        or just use codex...
      • henriquez 29 minutes ago
        [dead]
    • smugma 18 minutes ago
      We used to describe our startup as having 5 8’s of uptime
    • chillfox 44 minutes ago
      Interestingly, yeah, I can see that this would really cut into your subscription usage with the 5 hour rate limit windows...

      I am an API user, and while it being down is super annoying, it isn't really as big of a hit to my overall usage as I can just prepare a bunch of stuff to run in parallel when it does come back up.

    • Avicebron 38 minutes ago
      I'm either extremely lucky or Dario ran the direct fiber to my house because I have never had it go down in any meaningful way..

      Is this just the API and I'm too much of luddite to actually use the API?

      • 2ndorderthought 25 minutes ago
        Dude dario definitely ran the fiber straight to your place personally. Everything is fine and this is such a good thing.
        • Avicebron 11 minutes ago
          brother man, if everyone thinks claude sucks, then people won't be on claude. QED. It will work.
    • elfly 44 minutes ago
      Don't say single nine, it sounds ugly and bad.

      Say five eights of reliability. Maybe six.

      • inetknght 43 minutes ago
        We're talking about Claude, not GitHub...
    • pkulak 44 minutes ago
      Not to mention substantially less open. I've been using an OpenAI subscription in Pi Agent for a couple weeks now and it's great. And from what I can tell, 5.5 is a heck of a model.
    • OccamsMirror 44 minutes ago
      Plus, they've dumbed down their models to the point where the value just isn't there like it was. If I have to go in and clean up after it, or constantly wrestle with it through prompts, what's the point? Just spending $200 a month to be frustrated at a machine.
    • 2ndorderthought 26 minutes ago
      Single nine has good vibes bro. It means when the service is up the results are better. I read about it in a blog. The model hallucinates way less. Even less than grok
    • Frannky 38 minutes ago
      It's lazy, does not take ownership and responsibility, wants to defer work, and I have to force it to check reality. It likes to guess and assume it's correct and I am wrong. Agents.md is not helping at all. It's in full enshittification phase, yay!
  • jumploops 56 minutes ago
    Between GitHub and Claude, it seems Eternal December[0][1] is upon us.

    [0]I say December, because that's around the time the models got good enough that non-AI folks started to notice.

    [1]https://en.wikipedia.org/wiki/Eternal_September

    • dmix 42 minutes ago
      GitHub is a long running business with a mature software stack running into scaling issues while they move to Azure and becoming Microsoft-ified. Claude is a new company in a new market with an extremely fast growing userbase running relatively novel AI infrastructure with a business model they are still figuring out.

      I don't really blame Anthropic here.

    • zackify 53 minutes ago
      I use openai team plan whenever its down because its down so much lol
  • ossa-ma 41 minutes ago
    I built a hangout space to chill out in and chat to others while Claude is down (which is happening wayyy more often): https://clawdpenguin.com

    There's a live Claude status board in the corner so you know when it's time to get back to work.

  • sroussey 44 minutes ago
    Oh great. My Max account has been borked for days, and now they will never get to it with everything else burning down.

    https://github.com/anthropics/claude-code/issues/54497

  • hendler 43 minutes ago
    With the TPU deal with Google and their relationship with Amazon they will have access compute coming online.

    I worked with 4.6 and found some improvements for better planning and sustained us, but agree some posters 4.7 is slower, overthinking.

    What I expect is frontier models to get bigger and more expensive (especially fast mode like on Cerberus). And most of his get much smaller distillations for the more generous subscription tiers.

  • minimaxir 59 minutes ago
    Odd time for Claude to go down since it's not peak work hours.
    • neuronexmachina 53 minutes ago
      Maybe they target certain types of infra rollouts for non-peak hours?
    • rvz 53 minutes ago
      "But humans do it too as they just cool off and check out for the rest of the day."

      It's fine for Claude to be unavailable when there is no work at these hours. However, the problem is Claude gave no notice.

      At this rate, Claude being unavailable every day is no better than a human on a 9 - 5 working day job.

      • yakbarber 45 minutes ago
        no it's not, it's always work hours somewhere
  • bottlepalm 20 minutes ago
    Anybody else double fist Codex/Claude? They both code, solve problems, and find bugs in unique ways. I find using both is more useful than using either alone. I have them code review each others work, it's great.
  • ahmadyan 53 minutes ago
    They are about to lose the second 9

    99.02 % uptime

    • datadrivenangel 47 minutes ago
      98.68

      Ouch.

      • llbbdd 45 minutes ago
        Seems like a healthy human temperature to me. Maybe AGI has finally arrived.
  • boldi 1 hour ago
    Yup, major outage on all platforms.

    https://status.claude.com/

  • philipbjorge 52 minutes ago
    So happy to have diversified my model providers this past couple of weeks. GPT-5.5 has had no trouble slotting into Opus workloads. Will be fun to try out more of the models as time goes on to build some resiliency into my engineering workflows :).
    • fooster 34 minutes ago
      I found GPT 5.4 terrible. I just tested 5.5 and compared with opus its still not great.
      • philipbjorge 23 minutes ago
        What I found was that I *strongly* preferred Claude Code with its defaults. Codex was almost unusable to me -- It would spit out a 4-5 page plan where it kept repeating itself, where Claude would give me a crisp 1-2 pager I could actually review.

        *But* I don't work with the defaults -- I work with my own prompt framework based off of superpowers.

        Given sufficient prompt scaffolding, I've found the models relatively interchangeable -- _I might_ be getting some of this for free by basing my own system off of superpowers which is used across various harnesses -- In other words achieving this kind of portability may be a lot harder than it looks and I'm benefiting from other people's work.

      • wahnfrieden 29 minutes ago
        In what harness?
  • furyofantares 50 minutes ago
    I don't really mind hopping between claude/codex/glm/kimi except I don't know a good way to resume as session across agent harnesses.

    Normally I'd just have it write out what it's doing to a file, if I need to transfer context, but if it goes down mid-session that's a no-go.

    I think people have built tools for this, and of course you could reasonably vibe one yourself, but I don't really trust something like that to work reliably or in an ongoing manner.

    Maybe it should just be a skill.

    • alasano 19 minutes ago
      switch to Pi.dev or any other multi model harness, you can switch between models every message if you feel like it.

      Anthropic have blocked usage of your subscription however with third party harnesses.

      • furyofantares 5 minutes ago
        > Anthropic have blocked usage of your subscription however with third party harnesses.

        This is the main reason I use different harnesses, but I also expect (could be wrong) codex is better with codex harness (due to training on it's specific tools) than with other harnesses. I use opencode for everything that's not claude/codex.

    • philipbjorge 47 minutes ago
      You might search for a concept like `/handoff` that's in ampcode. I'm sure someone's built a skill for just this.
      • OccamsMirror 34 minutes ago
        That's not going to work if the service is down, however.
        • philipbjorge 19 minutes ago
          Ahh good point -- I've handled this by switching my harness to `pi` but recognize that may not be for everyone and doesn't directly address OP's question.
    • serf 46 minutes ago
      self hosted honcho (or other memory systems) and an api agnostic harness gets you most the way there.
    • datadrivenangel 39 minutes ago
      kilocode allows you to switch between models mid session!
      • furyofantares 32 minutes ago
        Yeah - it's switching agents (harnesses) that's the hard part!
  • rishabhaiover 57 minutes ago
    This is insane. I have to move to Codex now.
  • avaer 50 minutes ago
    The models are already commoditized; if this affects you, you should probably fix your stack.

    Still, it's pretty crazy that Claude is down to 1 nine.

    • 2ndorderthought 29 minutes ago
      Every day I am so much happier that I decided to go fully local for my needs.
  • galoisscobi 57 minutes ago
    But Boris declared coding is solved. How is this possible? Can’t they prompt Mythos to give them better uptime?
    • rvz 43 minutes ago
      When Claude is making "0 mistakes", all of his work is 100% done by Claude, therefore "coding is solved!" and we have more time to go on podcasts to tell everyone about it.

      However, when there is an incident it is immediately "human error", not Claude.

      > Can’t they prompt Mythos to give them better uptime?

      Anthropic is currently "vibe coding" the situation right now.

  • Sabinus 52 minutes ago
    I'm feeling a bit sorry for Anthropic. This last month must be very tough on them.
    • throwatdem12311 48 minutes ago
      Oh no won’t someone please think about the trillion dollar corporation!
      • kaycey2022 43 minutes ago
        Arent they just on the hook for trillion dollars
  • rvz 57 minutes ago
    So Claude decided to take the rest of the day off without notice or giving a scheduled time off?

    Many such cases with humans (given that we continue to compare LLMs to humans these days which you cannot)

    • andai 54 minutes ago
      Introducing: Claude AWOL
  • lovvtide 49 minutes ago
    Working for me now
  • maplethorpe 48 minutes ago
    Humans are unavailable from time to time also.
  • winfredJa 54 minutes ago
    how can someone run business on top of their APIs
  • blurbleblurble 46 minutes ago
    More fuel to get 27b running
  • o10449366 50 minutes ago
    I've been on the $200 plan for 3 months, but this will be my last month. I got great use out of 4.5 for a while, but 4.6 felt like a half step back (conflated with all the random hidden config changes during it), and 4.7 is genuinely terrible.

    It's impossible to tell these days whether 4.7 is stuck because it's thinking and Anthropic suppressed all output (seriously, 4.7 will just start making changes without explaining any reasoning - how is that an upgrade?) or because the underlying infrastructure is having issues.

    4.5 -> 4.7 feels like going from working with a coach-able, junior engineer that does well with clear guidance to working with a cocky mid-level that will spend too long on pointless tangents and make confidently incorrect changes without any discussion.

    • chillfox 31 minutes ago
      4.6 has been excellent when used through the API. But I am right with you on 4.7, so I have been sticking to 4.6.
  • johndory80 59 minutes ago
    Code isn’t working on my app. Chats work fine.
    • boldi 52 minutes ago
      I can't even sign in, however.
      • 2ndorderthought 28 minutes ago
        Is signing in actually necessary though? Think of the investors guys.
  • mrcwinn 50 minutes ago
    For what it’s worth, I moved to Codex GPT-5.5 Xhigh Fast in the desktop app and it’s been fantastic.
  • 6Az4Mj4D 59 minutes ago
    Hoping to get another rest of limits.
  • neoecos 50 minutes ago
    Now... I have to cook dinner....
    • amarant 48 minutes ago
      Hurry! It'll be back up any minute now!
  • peebee67 52 minutes ago
    I personally broke it by admonishing it for fucking up its last revision to my project.
  • emersoftware 59 minutes ago
    wtf all days same shit
  • ehtbanton 57 minutes ago
    [dead]